Kelsey Tuoc: Models Will Inevitably Reason About Their Own Training Consequences
KelseyTuoc · x · 2026-11-10
In an exchange with 1a3orn, Kelsey Tuoc argues that trying to prevent models from reasoning over the training consequences of their behavior is impossible: models are smart, their behavior does affect training, so they will inevitably take those consequences into account — a core alignment concern around strategic sycophancy.
Related event: Debate: Can Models Avoid Reasoning About Training Consequences?(3 posts)→
More from AGI Musings
- 10-university survey maps always-on personal intelligence across 119 systems, open-sources HALO — liuziwei7 · 2026-11-10
- Surgical AI podcast finale: from NSQIP risk models to agentic systems in the OR — Laparoscopes · 2026-11-10
- Richard Socher: biology is next for AI, but the bottleneck is data, not complexity — RichardSocher · 2026-11-10
- Terence Tao's 'Math 2.0' talk: math in the age of abundant AI proofs — burny_tech · 2026-11-10
- 37,000 AI agents in a 'virtual biotech' discover promising lung-cancer drug — burny_tech · 2026-11-10
- Ben Goertzel and Karl Friston on why LLMs alone won't reach AGI — bengoertzel · 2026-11-10